jurevreca12

Perhaps you are failing to take into account the scaling factors? When you save the weights they are "quasi" quantized, they are actually floats that can only take up a...

When you set alpha equal to a tensor, then they will be the (constant) scaling factor(there is a separate variable in the code called _scale_). However, this is not really...

It is a little misleading in some cases yes. But maybe you are looking it from a perspective of whole numbers. If you consider the quantizer as a fixed-point quantizer...

With quantized_bits(bits=8, integer=7, keep_negative=True) you will get 2^bits different **uniformly distributed** values. These weights can be represented with an 8 bit signed (twos complement) number in hardware. Regarding the scaling....

I am not an author of QKeras, but I would imagine getting these networks to run on a GPU is non-trivial. Quantization-aware training is more of a research field, so...

@YogaVicky Yes. You can see the scale being used in the "scale" variable of the quantizer. But depending on the configuration the scale can be recomputed depending on the inputs.

You can use the predict method, as QKeras is just an extension of Keras.

@mattvenn Hey matt, did you maybe manage to fix this issue? (Conflict found...) I am getting the same issue.

@vijayank88 I noticed one thing after closing the issue. I commented out the macro set ::env(FP_PDN_MACRO_HOOKS) . If I don't do that i still get the same error as Matt....

https://github.com/The-OpenROAD-Project/OpenLane/issues/1104